Michael Stanley Gee

Thin-slice MRI may improve appendix visualization in children with suspected appendicitis, but reducing slice thickness decreases signal-to-noise ratio (SNR) and can degrade image quality. Deep learning reconstruction (DLR) enables denoising of thin-slice images and may mitigate these limitations. To evaluate whether 2-mm T2-weighted magnetic resonance imaging (MRI) with DLR improves appendix visualization and diagnostic performance compared with conventional 4-mm MRI in pediatric appendicitis. In this prospective, Institutional Review Board-approved, single-center study (January 2022-June 2025), 82 pediatric patients (mean age 9.6 years; age range 5-20 years) undergoing MRI for suspected appendicitis were included. MRI protocols contained both standard 4-mm and thin-slice 2-mm single-shot T2-weighted images; DLR was applied to 2-mm images (2-mm+DLR). Three blinded radiologists independently assessed paired series for appendix visualization, confidence, appendicitis diagnosis, ancillary findings, and overall image quality. Objective SNR was measured in psoas muscle, bladder, and fat. Diagnostic performance was calculated against surgical or clinical reference standards using paired statistical tests. In the first 16 exploratory cases, quantitative analysis showed that the signal-to-noise ratio of 2-mm+DLR images was comparable to that of standard 4-mm images. Across the full cohort, pooled analysis showed improved appendix visualization with 2-mm+DLR compared with standard 4-mm MRI (88.2% [217/246] vs 83.3% [205/246], P=0.006). Overall diagnostic image quality was also higher with 2-mm+DLR (median 5 vs 4, P0.1). Exploratory pooled diagnostic performance numerically favored 2-mm+DLR, with higher sensitivity (89% [78/87] vs 81% [71/87]) and accuracy (89% [218/246] vs 86% [210/246]), although paired comparisons did not reach statistical significance (Table 4). DLR-enhanced 2-mm MRI improves appendix visualization and overall diagnostic image quality in pediatric appendicitis without reducing reader confidence or specificity. Thin-slice DLR MRI supports improved depiction of the appendix and alternative abdominal pathology in children.

Due to increasingly nuanced Crohn disease therapy selection and disease evaluation, radiologic assessment of transmural healing, although aspirational, may be more complete than endoscopic assessment of mucosal healing, which is the current treatment target.

This narrative review examines strategies and recommendations to address the current radiologist shortage in the USA, with a particular emphasis on workforce retention and preservation through operational efficiency, organizational leadership, cultural transformation, and technology integration. National workforce data, expert commentaries, and strategic frameworks from academic radiology and healthcare leadership literature were reviewed to contextualize current challenges and proposed solutions. The radiology workforce faces escalating pressure driven by rapidly increasing imaging volumes, limited growth in the number of practicing radiologists, and rising attrition rates. Between 2008 and 2018, radiologist workloads nearly doubled while workforce expansion was much smaller, exacerbating workload imbalance, burnout, and professional dissatisfaction. The COVID-19 pandemic exacerbated workforce challenges by causing an exodus of workers and making on-site work more challenging. Although short-term mitigation strategies exist, sustainable long-term solutions require coordinated cultural and structural changes that prioritize strategic hiring, transparent career advancement pathways, protected academic and professional development time, and optimized workflow efficiency supported by technology. In conclusion, effective management of the radiology workforce shortage necessitates integrated operational and cultural approaches, with departments implementing comprehensive and tailored interventions to expand workforce capacity, enhance professional fulfillment, and maintain high-quality patient care.

Background Small bowel strictures are a common and challenging complication of Crohn’s disease (CD), and predicting their responsiveness to medical therapy remains an unmet clinical need. Objective Strictures, defined by the CONSTRICT consensus as a localized segment demonstrating luminal narrowing and bowel wall thickening, accompanied by pre-stenotic dilation, are a common feature of CD, impairing bowel function, complicating treatment, and often leading to surgery. Predicting which lesions are responsive to medical therapy and which will become obstructive represents an important clinical goal. We aim to characterize ileal strictures in patients with CD by exploring the bowel wall motility in patients receiving biologic agents and evaluating motility’s potential role in predicting therapeutic response compared with standard MRE biomarkers. Materials and methods This retrospective study included subjects between 10-28 years of age with stricturing CD receiving immunotherapy who underwent modification or escalation of biologic therapy and clinically indicated magnetic resonance enterography within a 2-month window. All included patients had ileal strictures identified on magnetic resonance enterography (MRE) based on CONSTRICT criteria. Demographic and clinical variables of the overall cohort were obtained. Clinical response and disease activity were evaluated up to 6 months after therapy initiation or adjustment. Subjects were categorized as “non-responders” if they experienced worsening disease activity, required discontinuation of therapy, or needed surgical intervention. Simplified MR indexes of activity (sMaRIA) assessed the ileum, and motility data were processed using GIQuant® (Motilent Ltd., London, UK) software. Stricture length, volume, wall thickness, and T2 signal intensity were also measured using Motilent® software tools. Statistical analyses included t-tests or Mann-Whitney U tests for continuous variables, chi-square or Fisher’s exact tests for categorical variables, and ROC curve analysis to evaluate the diagnostic performance of motility and sMaRIA metrics in predicting treatment response. Significance was set at pn=21] female; mean age 19.77±5.13) were included, with 15 (37.5%) classified as non-responders. No significant differences were observed in age (P=0.60), sex (P=0.94), stricture length (P=0.64), wall thickness (P=0.34), stricture volume (P=0.42), or T2-weighted signal intensity (P=0.31). However, mean motility (176.03±128.63 vs. 67.83±33.88; P=0.006) and its standard deviation (72.06±55.55 vs. 30.27±25.79; P=0.02) were significantly higher in responders. sMaRIA scores were not significantly different between groups (mean 2.75 vs. 3.13; P=0.36). Motility outperformed sMaRIA (AUC 0.812 vs. 0.613; P=0.07) in predicting responses. Conclusion Quantitative MRI motility assessment was superior to traditional MRI biomarkers in predicting response to biologic therapy in adolescents and young adults with stricturing CD. Graphical Abstract

BACKGROUND AND PURPOSE: Gadolinium-based contrast agents (GBCAs) are essential in pediatric neuroimaging, enabling visualization of pathology that disrupts the blood–brain barrier. Gadopiclenol is a new macrocyclic GBCA with higher T1 relaxivity, permitting a 50% dose reduction while maintaining diagnostic quality. However, it is unknown whether this higher relaxivity alters background extra-axial vascular enhancement. We hypothesized that gadopiclenol, despite its lower dose, would increase background enhancement on post-contrast pediatric brain MRI compared to gadoterate meglumine (Gd-DOTA). MATERIALS AND METHODS: In this retrospective observational study, 302 contrast-enhanced brain MRI studies in patients aged 2–18 years were reviewed: 151 with gadopiclenol (0.05 mmol/kg) and 151 with Gd-DOTA (0.1 mmol/kg). Post-contrast sequences included 3D T1 spin echo (SE), 3D T1 gradient echo (SPGR), 2D T1 turbo spin echo (TSE), and 2D FLAIR. Two neuroradiologists established binary enhancement categories based on sulcal enhancement thresholds (high vs. low). One reader assigned scores for all studies; a second reader evaluated a subset for interobserver agreement. Logistic regression assessed the association between contrast agent and high enhancement, adjusting for age, sex, anesthesia, and scanner field strength. RESULTS: Gadopiclenol was independently associated with significantly greater odds of high extra-axial enhancement on all T1-weighted sequences: 3D T1 SE (OR = 10.2, p < 0.001), 3D T1 SPGR (OR = 10.7, p < 0.001), and 2D T1 TSE (OR = 14.0, p < 0.001). Anesthesia was also an independent predictor of high enhancement on 3D SE and SPGR. On 2D FLAIR, contrast agent had no effect; instead, younger age was associated with high enhancement (p = 0.022), with an age–anesthesia interaction suggesting attenuation of this effect under sedation. Interobserver agreement was moderate to substantial (κ = 0.530–0.632). CONCLUSIONS: Gadopiclenol increases background extra-axial enhancement on T1-weighted post-contrast sequences in pediatric brain MRI, likely reflecting its higher relaxivity. Radiologists should be aware of this effect to avoid misinterpretation as leptomeningeal pathology. Post-contrast FLAIR remains unaffected and continues to serve as a reliable sequence for detecting true meningeal disease. ABBREVIATIONS: GBCA＝ gadolinium-based contrast agent; SE＝ spin echo; SPGR＝ spoiled gradient echo; TSE＝ turbo spin echo.

Background Deep learning (DL) reconstructions have shown utility for improving image quality of abdominal MRI in adult patients, but a paucity of literature exists in children. Objective To compare image quality between three-dimensional fast spoiled gradient echo (SPGR) abdominal MRI acquisitions reconstructed conventionally and using a prototype method based on a commercial DL algorithm in a pediatric cohort. Materials and methods Pediatric patients (age < 18 years) who underwent abdominal MRI from 10/2023–3/2024 including gadolinium-enhanced accelerated 3D SPGR 2-point Dixon acquisitions (LAVA-Flex, GE HealthCare) were identified. Images were retrospectively generated using a prototype reconstruction method leveraging a commercial deep learning algorithm (AIR™ Recon DL, GE HealthCare) with the 75% noise reduction setting. For each case/reconstruction, three radiologists independently scored DL and non-DL image quality (overall and of selected structures) on a 5-point Likert scale (1-nondiagnostic, 5-excellent) and indicated reconstruction preference. The signal-to-noise ratio (SNR) and mean number of edges (inverse correlate of image sharpness) were also quantified. Image quality metrics and preferences were compared using Wilcoxon signed-rank, Fisher exact, and paired t-tests. Interobserver agreement was evaluated with the Kendall rank correlation coefficient (W). Results The final cohort consisted of 38 patients with mean ± standard deviation age of 8.6 ± 5.7 years, 23 males. Mean image quality scores for evaluated structures ranged from 3.8 ± 1.1 to 4.6 ± 0.6 in the DL group, compared to 3.1 ± 1.1 to 3.9 ± 0.6 in the non-DL group (all P < 0.001). All radiologists preferred DL in most cases (32–37/38, P < 0.001). There were a 2.3-fold increase in SNR and a 3.9% reduction in the mean number of edges in DL compared to non-DL images (both P < 0.001). In all scored anatomic structures except the spine and non-DL adrenals, interobserver agreement was moderate to substantial (W = 0.41–0.74, all P < 0.01). Conclusion In a broad spectrum of pediatric patients undergoing contrast-enhanced Dixon abdominal MRI acquisitions, the prototype deep learning reconstruction is generally preferred to conventional methods with improved image quality across a wide range of structures. Graphical Abstract

Amniotic fluid volume (AFV) is a critical indicator of fetal health, traditionally assessed using ultrasound-based methods, which are limited by operator dependency and 2D measurements. While MRI offers superior tissue characterization, it remains underutilized for AFV assessment due to labor-intensive manual segmentations. Pulse sequence variations in MRI can significantly influence image contrast through T1 and T2 weighting and potentially cause signal dropout in certain regions, making automated analysis challenging. To address these challenges, we present ARANet (Adaptive Resolution Attention Network), featuring a novel adaptive resolution attention module that uniquely combines adaptive resolution processing with channel-wise attention mechanisms for precise MRI-based segmentation. In extensive evaluations, ARANet demonstrates superior performance with a Dice score of 0.961 at full brightness, maintaining robust performance (0.909) even at 30% brightness, significantly outperforming existing models in challenging low-contrast conditions. We introduce FAFO_3D, a new metric integrating amniotic fluid overlap, fetal age, and volume, which achieves 100% accuracy in clinical AFV classification (normal, oligohydramnios, and polyhydramnios) when combined with a support vector classifier. A comprehensive web platform automates the workflow from DICOM processing to analysis, providing detailed reports and 3D visualizations for clinical implementation. This solution offers a novel, accurate, and clinically applicable approach for AFV assessment, though further validation in diverse clinical environments is recommended.

Background The scout accelerated motion estimation and reduction (SAMER) method has been developed to achieve rapid retrospective motion correction and may be advantageous in pediatric imaging to mitigate motion artifacts. Objective To evaluate the efficacy of SAMER for motion correction of brain imaging in awake pediatric patients. Methods In this institutional review board (IRB) approved and Health Insurance Portability and Accountability Act (HIPAA) compliant prospective study, 33 pediatric patients were scanned on a 3-T MRI system in the outpatient setting. The imaging protocol included an accelerated 3D T1-weighted SAMER MPRAGE research sequence acquired in 2 min 37 s. Retrospective reconstructions of the T1-weighted MPRAGE data were performed with and without SAMER motion correction. Reconstructed image pairs were reviewed side-by-side by two board-certified neuroradiologists in a blinded manner and graded for motion artifacts using a 5-point scale. The improvement in motion score was calculated by subtracting the post-correction score from the pre-correction score. Results Without SAMER motion correction, 24 out of 33 cases (73%) showed motion artifact (21% (7/33) minimal, 27%(9/33) mild, 9% (3/33) moderate, and 15% (5/33) severe). SAMER motion correction improved motion artifacts in 79% (19/24) of cases, improving the motion score by median of 3 vs. 2 for motion-corrected examinations using SAMER. After applying SAMER motion correction, 50% (4/8) of cases considered nondiagnostic due to motion were reclassified as diagnostic. Conclusion SAMER demonstrates potential for reducing motion artifacts in 3D T1-weighted MPRAGE brain MR images, with the most notable improvements occurring in cases of moderate to severe motion.